| Conference |
| Type of Publication |
| A New Similarity Measure for Sub-Pixel Accurate Motion
Analysis in Object-Based Coding |
| Title |
|
Peter H. N. de With
|
| Authors |
| 5th World Multi-Conference on Systemics, Cybernetics
and Informatics (SCI), pp.
244-249, Orlando, FL, July 2001 |
| Published in |
| A new similarity measure for
motion-estimation and motion-compensated segmentation
applications is presented. The new measure shows low sensitivity
to image noise, is more tolerant to small errors in the motion
model and it provides a sub-pixel accuracy which is comparable to
conventional measures like mean-square error. The proposed
measure shows a linear increase of error as a function of the
displacement. This beneficial property has been exploited to
design a novel motion-estimation algorithm with fast
convergence. |
| Abstract |
|
sub-pixel motion-estimation
similarity-measures
segmentation
|
| Keywords |
| [PDF]
[BIB] [XML] |
| Downloads & Bib-Entries |
